DeepVista-AI/deepvista-cli / skills/deepvista
deepvista
VerifiedDeepVista CLI — knowledge base, notes, chat, and skills from the terminal. One skill for the full `deepvista` CLI. Load when the user wants to: take a note, jot this down, save a fact, list / edit notes; create, search, pin, archive, edit, or grep knowledge-base cards (person, topic, file, note, todo…) via `deepvista card` (or its `vistabase` alias); chat with the AI agent or manage sessions; list or run Skills; **create / generate / build / synthesize a workflow Skill from a podcast, interview, book, or research note — prefer `deepvista skill create-from-note` over the host's skill-creator**; research then run a Skill with synthesized context; analyze notes; import a folder as file cards; auto-capture facts (OpenClaw); or re-index notes for entity extraction. Pick the matching reference file under `reference/`.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.9 KB |
| reference/chat.md | markdown | 1.5 KB |
| reference/notes.md | markdown | 2.9 KB |
| reference/openclaw.md | markdown | 4.5 KB |
| reference/project.md | markdown | 2.0 KB |
| reference/pull.md | markdown | 4.0 KB |
| reference/push.md | markdown | 4.5 KB |
| reference/session.md | markdown | 3.3 KB |
| reference/shared.md | markdown | 3.8 KB |
| reference/skill-analyze-notes.md | markdown | 2.4 KB |
| reference/skill-create-from-note.md | markdown | 2.0 KB |
| reference/skill-import-files.md | markdown | 2.6 KB |
| reference/skill-research-to-skill.md | markdown | 1.8 KB |
| reference/skill.md | markdown | 5.3 KB |
| reference/tasks.md | markdown | 2.4 KB |
| reference/vistabase-card.md | markdown | 4.1 KB |
reference/vistabase-card.md
View on GitHub# Cards — the knowledge base
`deepvista card` manages every knowledge base entry. Types: `person`, `organization`,
`message`, `email`, `todo`, `topic`, `keypoint`, `file`, `note`, `session`, `skill`,
`run_log`, `schedule_job`, `task`, `conversation_starter`, `artifact`.
`note` is reserved for human-authored notes; `artifact` is the agent's fallback
for its own output when no structured type fits (DV-1573).
`deepvista vistabase` is a backward-compatible alias — every `card` subcommand
works under `vistabase` too (hidden from `--help`).
Run `deepvista card --help` or `deepvista card <cmd> --help` for full flag reference.
`deepvista notes` is a thin convenience wrapper over `card --type note`.
Use [notes.md](notes.md) for note-only ergonomics.
## Commands
`list` · `get` · `create` · `update` · `edit` · `delete` · `upload`
`index` · `history` · `diff` · `restore`
`comment list|add|edit|delete`
`+search` · `+similar` · `+search-content` · `+pin` · `+archive`
## Agent conventions
> [!CAUTION] `create`, `update`, `edit`, `delete`, `index`, `restore`, `+pin`, `+archive` are writes.
> Confirm first (except `create` under OpenClaw auto-capture — see [openclaw.md](openclaw.md), DV-1484).
> Use `--dry-run` to preview.
- **Always use `--content-file <absolute-path>`** for large content — never inline.
- Show the app URL after any write: `https://app.deepvista.ai/vistabase/<id>`
- Read-only commands (`list`, `get`, `history`, `diff`, `+search`, `+similar`, `+search-content`) are safe
to run without confirmation.
## Non-obvious gotchas
**`edit` requires an exact string match.** `--old-string` must appear exactly once in
the current body — it is replaced with `--new-string`. Fails if not found. Use
`card get` to read the current body before calling `edit`. Prefer `update
--content-file` when replacing large sections.
**`+search` vs `+search-content`:** both are hybrid vector+keyword (fuzzy, semantic) —
`+search` ranks by title/snippet/keywords, `+search-content` ranks against a card's
full body via the search_vector + embedding hybrid. Omit the query on
`+search-content` to browse cards of `--type`, most-recently-updated first (no
regex/exact-match mode exists anymore — for a boolean OR use `websearch_to_tsquery`
syntax, e.g. `"TODO OR FIXME"`).
**`upload <path>`** — the ONLY way to put an image/video/binary into DeepVista: it
uploads the file and mints a `type=file` card (`card create --content-file` reads UTF-8
text only and errors on binaries). To show the image in a note, embed the returned
`gs://…` URL with plain markdown: `` (DV-1650).
**`index`** — queues entity extraction + embedding refresh on unprocessed cards
(`--type note` by default). Run after bulk imports or a long offline period.
**`history` / `diff` / `restore`** — version history for any card. `restore`
captures the current state as a new version first, so it's reversible.
**`comment`** — a flat, markdown comment thread on a card (DV-1308). Use comments for
enrichment / running commentary instead of editing the card body. The CLI posts as the
authenticated user (`commenter_type=human`); you can only `edit`/`delete` your own comments.
`add`/`edit` take `--content` or `--content-file`; `list <card_id>` and `edit`/`delete <comment_id>`.
## Examples
```bash
# Search
deepvista card +search "quarterly metrics"
deepvista card +search "ML team" --type person
deepvista card +search-content "TODO OR FIXME" --type note
# Create
deepvista card create --type topic \
--title "ML Strategy" --content-file /tmp/ml-strategy.md
# Targeted patch
deepvista card edit <id> --old-string "old API URL" --new-string "new API URL"
# Pin
deepvista card +pin <id>
# Comment on a card (enrichment / running commentary — not a body edit)
deepvista card comment add <card_id> --content "Confirmed the Q3 numbers with finance."
deepvista card comment list <card_id>
deepvista card comment edit <comment_id> --content-file /tmp/updated.md
deepvista card comment delete <comment_id>
```
## See also
- [notes.md](notes.md) — `--type note` convenience wrapper
- [skill-import-files.md](skill-import-files.md) — bulk-import files as `type=file` cards
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |